os-loop

A command that runs a complete cycle for improving an operating system for coding agents. It executes work, checks the results against a benchmark, records sources of difficulty, and reviews the cycle afterward.

In plain words
What is it for?
Use it to run tasks, evaluate proposed improvements, collect friction reports, save review results, update memory, and start a deeper retrospective when enough problems are found.
Why use it?
It keeps improvement work in one repeatable process and shows whether changes helped. It also records recurring problems so they can be addressed later.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/richfrem/agent-plugins-skills/os-loop
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.00124
Opus 5 $0.00020 $0.00062
Sonnet 5 $0.00008 $0.00025
Haiku 4.5 $0.00004 $0.00012

Measured 2d ago against content hash ab7d1a274631, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

os-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agent-agentic-os/commands/os-loop.md · 9 lines

What it actually says

/os-loop Command

Please run the os-improvement-loop skill immediately. Coordinate a full concurrent improvement cycle: execute tasks, evaluate against the benchmark (KEEP/DISCARD), emit friction events, close with post_run_metrics, save the self-assessment survey to retrospectives, persist memory, and trigger the Triple-Loop Retrospective if the friction threshold is crossed.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 9 lines · 40 tokens per session scan A ab7d1a274631

Subscribe to this mod's changes

os-loop is a command published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 124 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.